GPT-Realtime-2.1 mini
Model overview
gpt-realtime-2.1-mini
Distilled reasoning model for faster, lower-cost realtime voice interactions.
general LLMreasoningmultimodalaudiospeechrealtimeagentchatvoice assistantrealtime voiceenterprise access
Representative version
gpt-realtime-2.1-mini
| Company | OpenAI |
|---|---|
| Release | 2026-07-06 |
| Release type | Model release |
| Parameters | Not disclosed |
| Architecture | Not disclosed |
| Context | 128,000 |
| Input modalities | text / image / audio |
| Output modalities | text / audio |
| Tool use / function calling | Confirmed: Tool use, Function calling |
| Structured output / reasoning | Confirmed: Reasoning; Not shown: Structured output |
| Vision / audio / video | Confirmed: Vision, Audio; Not shown: Video |
| Open weights / License | No open weights / license not applicable openai-gpt-realtime-2-1-mini-current · License not applicable |
| Vendor API | Available GPT-Realtime-2.1 mini Model | OpenAI APIopenai-gpt-realtime-2-1-mini-current · 2026-07-06 |
| OpenRouter | Not separately listed on OpenRouter |
| Pricing | Official · 2026-07-08: $0.6 / $2.4 input / output, per 1M tokens |
| Benchmark | No reliable public source |
| Public signals | No reliable public source |
| Use cases | Realtime voice agents / Tool-using voice workflows / Low-latency spoken interaction / assistant chat |
| Claim evidence | Release / model specs / weightsGPT-Realtime-2.1 mini Model | OpenAI APIgpt-realtime-2.1-mini · 2026-07-06 |
OpenRouter
Pricing / context / availability
| OpenRouter | Not separately listed on OpenRouter |
|---|---|
| OpenRouter listing | Not separately listed in the current OpenRouter public list |
| Mapped version | gpt-realtime-2.1-mini openai-gpt-realtime-2-1-mini-current |
| Pricing | Official · 2026-07-08: $0.6 / $2.4 input / output, per 1M tokens |
| Context | 128000 |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-07-15T20:11:41.551Z |
| Source | View source |
Evidence gaps
Public display boundary
Parameter scale not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed